Training in progress, epoch 1

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1764e73963e690b8e90a5cad3c14f03f827662a1944a414fbe6e56cf9510c0b4
+oid sha256:4abb4f84d18d924b4324261651aeb4b349e1f2e36673ed57edf80b6a318be22e
 size 4877660776

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fdd1935192b5bb69026a5775b76fa9ab1a7770530b581a4aefe5fb234d10d1a4
+oid sha256:0faa2e8695bea0f7458653ef66c45ee522cd80f475082cd2bd8b82d6b6670c0d
 size 4932751008

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eaa6cb825a589043ef2be586293d77c461ce91590a0804bc2422938ac85d758
+oid sha256:ecfdf61386b9436db578f79844b9ffbd8c9fd342a7410fabd7ac11bdde4fb7ad
 size 4330865200

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8776da95c203c849b05a960badd4b063eea70a7937ca126a31d4f077edbfe4d0
+oid sha256:0f7f35e154be430bc931da12d16afb3f776838dfaedfb89ab62a3334ac44ecdc
 size 1089994880

trainer_log.jsonl

@@ -77,3 +77,84 @@
 {"current_steps": 77, "total_steps": 390, "loss": 0.4982, "lr": 3.885432320339167e-05, "epoch": 0.9856, "percentage": 19.74, "elapsed_time": "2:53:19", "remaining_time": "11:44:32"}
 {"current_steps": 78, "total_steps": 390, "loss": 0.4754, "lr": 3.879385241571817e-05, "epoch": 0.9984, "percentage": 20.0, "elapsed_time": "2:55:24", "remaining_time": "11:41:36"}
 {"current_steps": 79, "total_steps": 390, "loss": 0.4247, "lr": 3.873187606680543e-05, "epoch": 1.0112, "percentage": 20.26, "elapsed_time": "2:58:02", "remaining_time": "11:40:53"}
+{"current_steps": 80, "total_steps": 390, "loss": 0.4124, "lr": 3.866839912153168e-05, "epoch": 1.024, "percentage": 20.51, "elapsed_time": "2:59:54", "remaining_time": "11:37:10"}
+{"current_steps": 81, "total_steps": 390, "loss": 0.4155, "lr": 3.860342666498677e-05, "epoch": 1.0368, "percentage": 20.77, "elapsed_time": "3:01:51", "remaining_time": "11:33:44"}
+{"current_steps": 82, "total_steps": 390, "loss": 0.4229, "lr": 3.853696390206484e-05, "epoch": 1.0496, "percentage": 21.03, "elapsed_time": "3:03:52", "remaining_time": "11:30:40"}
+{"current_steps": 83, "total_steps": 390, "loss": 0.4184, "lr": 3.846901615704734e-05, "epoch": 1.0624, "percentage": 21.28, "elapsed_time": "3:05:59", "remaining_time": "11:27:57"}
+{"current_steps": 84, "total_steps": 390, "loss": 0.4226, "lr": 3.839958887317649e-05, "epoch": 1.0752, "percentage": 21.54, "elapsed_time": "3:08:03", "remaining_time": "11:25:04"}
+{"current_steps": 85, "total_steps": 390, "loss": 0.4102, "lr": 3.832868761221926e-05, "epoch": 1.088, "percentage": 21.79, "elapsed_time": "3:10:09", "remaining_time": "11:22:21"}
+{"current_steps": 86, "total_steps": 390, "loss": 0.4216, "lr": 3.825631805402182e-05, "epoch": 1.1008, "percentage": 22.05, "elapsed_time": "3:12:33", "remaining_time": "11:20:40"}
+{"current_steps": 87, "total_steps": 390, "loss": 0.4228, "lr": 3.818248599605448e-05, "epoch": 1.1136, "percentage": 22.31, "elapsed_time": "3:14:35", "remaining_time": "11:17:41"}
+{"current_steps": 88, "total_steps": 390, "loss": 0.4421, "lr": 3.810719735294731e-05, "epoch": 1.1264, "percentage": 22.56, "elapsed_time": "3:16:35", "remaining_time": "11:14:41"}
+{"current_steps": 89, "total_steps": 390, "loss": 0.4511, "lr": 3.8030458156016326e-05, "epoch": 1.1392, "percentage": 22.82, "elapsed_time": "3:18:41", "remaining_time": "11:11:59"}
+{"current_steps": 90, "total_steps": 390, "loss": 0.4335, "lr": 3.795227455278029e-05, "epoch": 1.152, "percentage": 23.08, "elapsed_time": "3:20:55", "remaining_time": "11:09:44"}
+{"current_steps": 91, "total_steps": 390, "loss": 0.4291, "lr": 3.787265280646825e-05, "epoch": 1.1648, "percentage": 23.33, "elapsed_time": "3:22:46", "remaining_time": "11:06:14"}
+{"current_steps": 92, "total_steps": 390, "loss": 0.4364, "lr": 3.7791599295517825e-05, "epoch": 1.1776, "percentage": 23.59, "elapsed_time": "3:25:01", "remaining_time": "11:04:06"}
+{"current_steps": 93, "total_steps": 390, "loss": 0.4341, "lr": 3.7709120513064196e-05, "epoch": 1.1904, "percentage": 23.85, "elapsed_time": "3:26:57", "remaining_time": "11:00:54"}
+{"current_steps": 94, "total_steps": 390, "loss": 0.3953, "lr": 3.762522306641998e-05, "epoch": 1.2032, "percentage": 24.1, "elapsed_time": "3:28:48", "remaining_time": "10:57:30"}
+{"current_steps": 95, "total_steps": 390, "loss": 0.4228, "lr": 3.7539913676545874e-05, "epoch": 1.216, "percentage": 24.36, "elapsed_time": "3:30:53", "remaining_time": "10:54:52"}
+{"current_steps": 96, "total_steps": 390, "loss": 0.4199, "lr": 3.745319917751229e-05, "epoch": 1.2288000000000001, "percentage": 24.62, "elapsed_time": "3:33:00", "remaining_time": "10:52:19"}
+{"current_steps": 97, "total_steps": 390, "loss": 0.405, "lr": 3.736508651595188e-05, "epoch": 1.2416, "percentage": 24.87, "elapsed_time": "3:35:11", "remaining_time": "10:50:01"}
+{"current_steps": 98, "total_steps": 390, "loss": 0.4219, "lr": 3.727558275050301e-05, "epoch": 1.2544, "percentage": 25.13, "elapsed_time": "3:37:06", "remaining_time": "10:46:53"}
+{"current_steps": 99, "total_steps": 390, "loss": 0.4071, "lr": 3.718469505124434e-05, "epoch": 1.2671999999999999, "percentage": 25.38, "elapsed_time": "3:39:08", "remaining_time": "10:44:08"}
+{"current_steps": 100, "total_steps": 390, "loss": 0.4382, "lr": 3.709243069912041e-05, "epoch": 1.28, "percentage": 25.64, "elapsed_time": "3:41:09", "remaining_time": "10:41:21"}
+{"current_steps": 101, "total_steps": 390, "loss": 0.4193, "lr": 3.699879708535838e-05, "epoch": 1.2928, "percentage": 25.9, "elapsed_time": "3:43:12", "remaining_time": "10:38:39"}
+{"current_steps": 102, "total_steps": 390, "loss": 0.4197, "lr": 3.69038017108759e-05, "epoch": 1.3056, "percentage": 26.15, "elapsed_time": "3:45:20", "remaining_time": "10:36:15"}
+{"current_steps": 103, "total_steps": 390, "loss": 0.4004, "lr": 3.680745218568026e-05, "epoch": 1.3184, "percentage": 26.41, "elapsed_time": "3:47:11", "remaining_time": "10:33:02"}
+{"current_steps": 104, "total_steps": 390, "loss": 0.412, "lr": 3.6709756228258735e-05, "epoch": 1.3312, "percentage": 26.67, "elapsed_time": "3:49:04", "remaining_time": "10:29:56"}
+{"current_steps": 105, "total_steps": 390, "loss": 0.4103, "lr": 3.6610721664960236e-05, "epoch": 1.3439999999999999, "percentage": 26.92, "elapsed_time": "3:50:59", "remaining_time": "10:26:59"}
+{"current_steps": 106, "total_steps": 390, "loss": 0.3937, "lr": 3.65103564293684e-05, "epoch": 1.3568, "percentage": 27.18, "elapsed_time": "3:53:00", "remaining_time": "10:24:17"}
+{"current_steps": 107, "total_steps": 390, "loss": 0.3802, "lr": 3.640866856166601e-05, "epoch": 1.3696, "percentage": 27.44, "elapsed_time": "3:55:06", "remaining_time": "10:21:50"}
+{"current_steps": 108, "total_steps": 390, "loss": 0.4054, "lr": 3.6305666207990886e-05, "epoch": 1.3824, "percentage": 27.69, "elapsed_time": "3:57:21", "remaining_time": "10:19:45"}
+{"current_steps": 109, "total_steps": 390, "loss": 0.4214, "lr": 3.6201357619783336e-05, "epoch": 1.3952, "percentage": 27.95, "elapsed_time": "3:59:27", "remaining_time": "10:17:20"}
+{"current_steps": 110, "total_steps": 390, "loss": 0.4101, "lr": 3.609575115312511e-05, "epoch": 1.408, "percentage": 28.21, "elapsed_time": "4:01:19", "remaining_time": "10:14:17"}
+{"current_steps": 111, "total_steps": 390, "loss": 0.4143, "lr": 3.598885526807003e-05, "epoch": 1.4208, "percentage": 28.46, "elapsed_time": "4:03:14", "remaining_time": "10:11:24"}
+{"current_steps": 112, "total_steps": 390, "loss": 0.3999, "lr": 3.5880678527966224e-05, "epoch": 1.4336, "percentage": 28.72, "elapsed_time": "4:05:01", "remaining_time": "10:08:11"}
+{"current_steps": 113, "total_steps": 390, "loss": 0.3852, "lr": 3.577122959877017e-05, "epoch": 1.4464000000000001, "percentage": 28.97, "elapsed_time": "4:06:47", "remaining_time": "10:04:57"}
+{"current_steps": 114, "total_steps": 390, "loss": 0.3902, "lr": 3.566051724835245e-05, "epoch": 1.4592, "percentage": 29.23, "elapsed_time": "4:08:56", "remaining_time": "10:02:42"}
+{"current_steps": 115, "total_steps": 390, "loss": 0.4163, "lr": 3.554855034579532e-05, "epoch": 1.472, "percentage": 29.49, "elapsed_time": "4:11:12", "remaining_time": "10:00:42"}
+{"current_steps": 116, "total_steps": 390, "loss": 0.4, "lr": 3.5435337860682304e-05, "epoch": 1.4848, "percentage": 29.74, "elapsed_time": "4:13:06", "remaining_time": "9:57:51"}
+{"current_steps": 117, "total_steps": 390, "loss": 0.4247, "lr": 3.532088886237956e-05, "epoch": 1.4976, "percentage": 30.0, "elapsed_time": "4:15:04", "remaining_time": "9:55:09"}
+{"current_steps": 118, "total_steps": 390, "loss": 0.4085, "lr": 3.520521251930941e-05, "epoch": 1.5104, "percentage": 30.26, "elapsed_time": "4:17:10", "remaining_time": "9:52:49"}
+{"current_steps": 119, "total_steps": 390, "loss": 0.4119, "lr": 3.5088318098215805e-05, "epoch": 1.5232, "percentage": 30.51, "elapsed_time": "4:19:13", "remaining_time": "9:50:19"}
+{"current_steps": 120, "total_steps": 390, "loss": 0.3952, "lr": 3.497021496342203e-05, "epoch": 1.536, "percentage": 30.77, "elapsed_time": "4:21:04", "remaining_time": "9:47:24"}
+{"current_steps": 121, "total_steps": 390, "loss": 0.4103, "lr": 3.485091257608047e-05, "epoch": 1.5488, "percentage": 31.03, "elapsed_time": "4:22:59", "remaining_time": "9:44:39"}
+{"current_steps": 122, "total_steps": 390, "loss": 0.4152, "lr": 3.473042049341474e-05, "epoch": 1.5615999999999999, "percentage": 31.28, "elapsed_time": "4:25:10", "remaining_time": "9:42:31"}
+{"current_steps": 123, "total_steps": 390, "loss": 0.4192, "lr": 3.4608748367954064e-05, "epoch": 1.5744, "percentage": 31.54, "elapsed_time": "4:27:31", "remaining_time": "9:40:43"}
+{"current_steps": 124, "total_steps": 390, "loss": 0.4056, "lr": 3.4485905946759965e-05, "epoch": 1.5872000000000002, "percentage": 31.79, "elapsed_time": "4:29:44", "remaining_time": "9:38:38"}
+{"current_steps": 125, "total_steps": 390, "loss": 0.3962, "lr": 3.4361903070645484e-05, "epoch": 1.6, "percentage": 32.05, "elapsed_time": "4:31:46", "remaining_time": "9:36:09"}
+{"current_steps": 126, "total_steps": 390, "loss": 0.4192, "lr": 3.423674967338681e-05, "epoch": 1.6128, "percentage": 32.31, "elapsed_time": "4:34:01", "remaining_time": "9:34:08"}
+{"current_steps": 127, "total_steps": 390, "loss": 0.4121, "lr": 3.411045578092754e-05, "epoch": 1.6256, "percentage": 32.56, "elapsed_time": "4:36:22", "remaining_time": "9:32:19"}
+{"current_steps": 128, "total_steps": 390, "loss": 0.4246, "lr": 3.398303151057543e-05, "epoch": 1.6383999999999999, "percentage": 32.82, "elapsed_time": "4:38:37", "remaining_time": "9:30:19"}
+{"current_steps": 129, "total_steps": 390, "loss": 0.4127, "lr": 3.385448707019199e-05, "epoch": 1.6512, "percentage": 33.08, "elapsed_time": "4:40:40", "remaining_time": "9:27:52"}
+{"current_steps": 130, "total_steps": 390, "loss": 0.3886, "lr": 3.372483275737468e-05, "epoch": 1.6640000000000001, "percentage": 33.33, "elapsed_time": "4:42:46", "remaining_time": "9:25:32"}
+{"current_steps": 131, "total_steps": 390, "loss": 0.4082, "lr": 3.359407895863199e-05, "epoch": 1.6768, "percentage": 33.59, "elapsed_time": "4:44:45", "remaining_time": "9:22:59"}
+{"current_steps": 132, "total_steps": 390, "loss": 0.4038, "lr": 3.34622361485514e-05, "epoch": 1.6896, "percentage": 33.85, "elapsed_time": "4:46:42", "remaining_time": "9:20:22"}
+{"current_steps": 133, "total_steps": 390, "loss": 0.4084, "lr": 3.332931488896029e-05, "epoch": 1.7024, "percentage": 34.1, "elapsed_time": "4:48:52", "remaining_time": "9:18:11"}
+{"current_steps": 134, "total_steps": 390, "loss": 0.3888, "lr": 3.319532582807977e-05, "epoch": 1.7151999999999998, "percentage": 34.36, "elapsed_time": "4:50:33", "remaining_time": "9:15:05"}
+{"current_steps": 135, "total_steps": 390, "loss": 0.4106, "lr": 3.30602796996717e-05, "epoch": 1.728, "percentage": 34.62, "elapsed_time": "4:52:37", "remaining_time": "9:12:44"}
+{"current_steps": 136, "total_steps": 390, "loss": 0.4164, "lr": 3.2924187322178865e-05, "epoch": 1.7408000000000001, "percentage": 34.87, "elapsed_time": "4:54:46", "remaining_time": "9:10:32"}
+{"current_steps": 137, "total_steps": 390, "loss": 0.3958, "lr": 3.278705959785821e-05, "epoch": 1.7536, "percentage": 35.13, "elapsed_time": "4:56:39", "remaining_time": "9:07:49"}
+{"current_steps": 138, "total_steps": 390, "loss": 0.4283, "lr": 3.2648907511907544e-05, "epoch": 1.7664, "percentage": 35.38, "elapsed_time": "4:58:51", "remaining_time": "9:05:45"}
+{"current_steps": 139, "total_steps": 390, "loss": 0.3929, "lr": 3.250974213158555e-05, "epoch": 1.7792, "percentage": 35.64, "elapsed_time": "5:00:55", "remaining_time": "9:03:23"}
+{"current_steps": 140, "total_steps": 390, "loss": 0.4083, "lr": 3.23695746053251e-05, "epoch": 1.792, "percentage": 35.9, "elapsed_time": "5:02:49", "remaining_time": "9:00:45"}
+{"current_steps": 141, "total_steps": 390, "loss": 0.4061, "lr": 3.222841616184025e-05, "epoch": 1.8048, "percentage": 36.15, "elapsed_time": "5:04:42", "remaining_time": "8:58:05"}
+{"current_steps": 142, "total_steps": 390, "loss": 0.4104, "lr": 3.208627810922665e-05, "epoch": 1.8176, "percentage": 36.41, "elapsed_time": "5:06:38", "remaining_time": "8:55:33"}
+{"current_steps": 143, "total_steps": 390, "loss": 0.4049, "lr": 3.194317183405573e-05, "epoch": 1.8304, "percentage": 36.67, "elapsed_time": "5:08:39", "remaining_time": "8:53:07"}
+{"current_steps": 144, "total_steps": 390, "loss": 0.4041, "lr": 3.1799108800462466e-05, "epoch": 1.8432, "percentage": 36.92, "elapsed_time": "5:10:36", "remaining_time": "8:50:36"}
+{"current_steps": 145, "total_steps": 390, "loss": 0.4046, "lr": 3.1654100549227024e-05, "epoch": 1.8559999999999999, "percentage": 37.18, "elapsed_time": "5:12:43", "remaining_time": "8:48:23"}
+{"current_steps": 146, "total_steps": 390, "loss": 0.4006, "lr": 3.1508158696850275e-05, "epoch": 1.8688, "percentage": 37.44, "elapsed_time": "5:14:46", "remaining_time": "8:46:04"}
+{"current_steps": 147, "total_steps": 390, "loss": 0.4084, "lr": 3.136129493462312e-05, "epoch": 1.8816000000000002, "percentage": 37.69, "elapsed_time": "5:16:44", "remaining_time": "8:43:35"}
+{"current_steps": 148, "total_steps": 390, "loss": 0.4043, "lr": 3.121352102768998e-05, "epoch": 1.8944, "percentage": 37.95, "elapsed_time": "5:18:36", "remaining_time": "8:40:58"}
+{"current_steps": 149, "total_steps": 390, "loss": 0.4058, "lr": 3.106484881410628e-05, "epoch": 1.9072, "percentage": 38.21, "elapsed_time": "5:20:39", "remaining_time": "8:38:38"}
+{"current_steps": 150, "total_steps": 390, "loss": 0.4019, "lr": 3.091529020389009e-05, "epoch": 1.92, "percentage": 38.46, "elapsed_time": "5:22:32", "remaining_time": "8:36:03"}
+{"current_steps": 151, "total_steps": 390, "loss": 0.4043, "lr": 3.076485717806808e-05, "epoch": 1.9327999999999999, "percentage": 38.72, "elapsed_time": "5:24:25", "remaining_time": "8:33:29"}
+{"current_steps": 152, "total_steps": 390, "loss": 0.4233, "lr": 3.061356178771564e-05, "epoch": 1.9456, "percentage": 38.97, "elapsed_time": "5:26:28", "remaining_time": "8:31:11"}
+{"current_steps": 153, "total_steps": 390, "loss": 0.4126, "lr": 3.0461416152991555e-05, "epoch": 1.9584000000000001, "percentage": 39.23, "elapsed_time": "5:28:34", "remaining_time": "8:28:57"}
+{"current_steps": 154, "total_steps": 390, "loss": 0.4159, "lr": 3.0308432462167045e-05, "epoch": 1.9712, "percentage": 39.49, "elapsed_time": "5:30:30", "remaining_time": "8:26:29"}
+{"current_steps": 155, "total_steps": 390, "loss": 0.4015, "lr": 3.015462297064936e-05, "epoch": 1.984, "percentage": 39.74, "elapsed_time": "5:32:26", "remaining_time": "8:24:00"}
+{"current_steps": 156, "total_steps": 390, "loss": 0.4277, "lr": 3.0000000000000004e-05, "epoch": 1.9968, "percentage": 40.0, "elapsed_time": "5:34:26", "remaining_time": "8:21:39"}
+{"current_steps": 157, "total_steps": 390, "loss": 0.3521, "lr": 2.98445759369477e-05, "epoch": 2.0096, "percentage": 40.26, "elapsed_time": "5:37:16", "remaining_time": "8:20:32"}
+{"current_steps": 158, "total_steps": 390, "loss": 0.3453, "lr": 2.9688363232396056e-05, "epoch": 2.0224, "percentage": 40.51, "elapsed_time": "5:39:27", "remaining_time": "8:18:27"}
+{"current_steps": 159, "total_steps": 390, "loss": 0.3449, "lr": 2.9531374400426158e-05, "epoch": 2.0352, "percentage": 40.77, "elapsed_time": "5:41:36", "remaining_time": "8:16:18"}
+{"current_steps": 160, "total_steps": 390, "loss": 0.3175, "lr": 2.9373622017294075e-05, "epoch": 2.048, "percentage": 41.03, "elapsed_time": "5:43:41", "remaining_time": "8:14:03"}